Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4081 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5483. Min Range: -5.5483
Max Act: 5.5483. Min Act: -0.1700
Data Index: 7953157 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5483. Min Range: -5.5483
Max Act: 5.2358. Min Act: -0.1700
Data Index: 6354740 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5483. Min Range: -5.5483
Max Act: 5.1421. Min Act: -0.1700
Data Index: 8157721 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5483. Min Range: -5.5483
Max Act: 5.1421. Min Act: -0.1700
Data Index: 4167597 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5483. Min Range: -5.5483
Max Act: 5.1108. Min Act: -0.1700
Data Index: 8164420 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5483. Min Range: -5.5483
Max Act: 5.0796. Min Act: -0.1700
Data Index: 3094109 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5483. Min Range: -5.5483
Max Act: 5.0796. Min Act: -0.1700
Data Index: 4119765 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5483. Min Range: -5.5483
Max Act: 5.0483. Min Act: -0.1700
Data Index: 4744244 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5483. Min Range: -5.5483
Max Act: 5.0483. Min Act: -0.1700
Data Index: 4323396 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5483. Min Range: -5.5483
Max Act: 5.0171. Min Act: -0.1700
Data Index: 6939747 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5483. Min Range: -5.5483
Max Act: 5.0483. Min Act: -0.1700
Data Index: 731751 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5483. Min Range: -5.5483
Max Act: 5.0483. Min Act: -0.1700
Data Index: 4119768 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5483. Min Range: -5.5483
Max Act: 4.9546. Min Act: -0.1700
Data Index: 4864930 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5483. Min Range: -5.5483
Max Act: 4.9233. Min Act: -0.1700
Data Index: 6913394 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5483. Min Range: -5.5483
Max Act: 4.9546. Min Act: -0.1700
Data Index: 5024170 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5483. Min Range: -5.5483
Max Act: 4.9233. Min Act: -0.1700
Data Index: 3580320 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5483. Min Range: -5.5483
Max Act: 4.9233. Min Act: -0.1700
Data Index: 8092794 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5483. Min Range: -5.5483
Max Act: 4.9233. Min Act: -0.1700
Data Index: 7191670 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5483. Min Range: -5.5483
Max Act: 4.9546. Min Act: -0.1700
Data Index: 566413 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5483. Min Range: -5.5483
Max Act: 4.9546. Min Act: -0.1700
Data Index: 189262 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19